Just like when multiple people gather simultaneously in a meeting room, higher-order interactions—where many entities interact at once—occur across various fields and reflect the complexity of real-world relationships. However, due to technical limitations, in many fields, only low-order pairwise interactions between entities can be observed and collected, which results in the loss of full context and restricts practical use. KAIST researchers have developed the AI model “MARIOH,” which can accurately reconstruct* higher-order interactions from such low-order information, opening up innovative analytical possibilities in fields like social network analysis, neuroscience, and life sciences.  *Reconstruction: Estimating/reconstructing the original structure that has disappeared or was not observed.

Chemical-free pesticides and integrated pest management are the need of the hour to limit the damage to the environment while improving food productivity. In a new study, researchers from Japan have turned their attention to aromatic bush basil plants to contain agricultural pests. They found that the volatile organic compounds emitted from bush basil could activate plant defense-related genes in the leaves of common bean plants cultivated closer to bush basil.

Wireless power transfer (WPT) systems deliver electricity without cables but often struggle with voltage stability when loads change. In this study, researchers developed a machine learning-based design method that uses numerical optimization to achieve load-independent operation. Their approach ensures stable output voltage (fluctuations under 5%) and high efficiency (86.7%) under varying loads. This breakthrough simplifies WPT design and could help create more practical, reliable wireless power systems for a wide range of applications.

The precise mechanism of cellular condensation and regeneration is not well-understood in organogenesis. For advances in regenerative medicine, understanding these mechanisms is crucial. In a new study, researchers used single-cell transcriptomics to understand the composition of human dental follicles and dental papillae. They found a PDGFRA⁺ mesenchymal stem cell with odontogenic potential that interacts with endothelial cells via paracrine signaling to stimulate angiogenesis, showing promise for future therapeutics in dental regenerative medicine.

Patients with microsatellite instability-high (MSI-H) tumors are likely to have better clinical outcomes than other patients. Recently, researchers from Yonsei University College of Medicine have proposed MSI-SEER, a novel AI model for accurate MSI prediction as well as immune checkpoint inhibitor responsiveness prediction. The innovative technology is expected to help battle gastric and colorectal cancers and further cancer research in general.

One of the best ways to protect artists’ creative work is to prevent it from ever being seen by “AI crawlers” – the programs that harvest data on the Internet for training generative models.  But most artists don’t have access to the tools that would allow them to take such actions.  And when they do have access, they don’t know how to use them. These are some of the conclusions of a study by a group of researchers at the University of California San Diego and University of Chicago, which will be presented at the 2025 Internet Measurement Conference in October in Madison, Wis.